granite 4.2 8b heretic needs about 7.2 GB of memory at Q4_K_M (a 5.3 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 7 quants, from 0.0 GB to 9.3 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 5.4 GB.
Granite 4.2 8B Heretic – abliterated, multilingual, tool‑aware LLM
Granite 4.2 8B Heretic is an abliterated build of IBM’s Granite 4.2 8B instruct model. It supports reasoning and tool calling across 12 languages. The model is released under Apache‑2.0 and is fully reproducible.
Good at
- Multilingual reasoning
- Tool‑based task execution
- Low refusal rate
Limits
- No vision support
- Requires 131072 token context
- No other licenses beyond Apache‑2.0
Best for
- Research on alignment techniques
- Creative writing with tool integration
- Unrestricted local inference
Who it’s for. Researchers and developers needing a multilingual, tool‑aware LLM without safety refusals. The model is suitable for local deployment and experimentation under an open license.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.0 GB | 1.8 GB | Fits | Get file → | |
| IQ3_M | 4.1 GB | 5.9 GB | Fits | Get file → | |
| IQ4_XS | 4.8 GB | 6.7 GB | Fits | Get file → | |
| Q4_K_M | 5.3 GB | 7.2 GB | Fits | Get file → | |
| Q5_K_M | 6.3 GB | 8.1 GB | Too big | Get file → | |
| Q6_K | 7.2 GB | 9.1 GB | Too big | Get file → | |
| Q8_0 | 9.3 GB | 11.2 GB | Too big | Get file → |
For 8 GB VRAM, use IQ4_XS (6.7 GB memory estimate). For 16 GB VRAM, Q4_K_M (7.2 GB) or Q5_K_M (8.1 GB) are suitable. For 32 GB VRAM, Q6_K (9.1 GB) or Q8_0 (11.2 GB) provide higher fidelity.
What GPU do you need for granite 4.2 8b heretic?
These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.
- 4 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 1.8 GB in use).
- 6 GB VRAM: the best quant that fits is IQ3_M (4.1 GB file, about 5.9 GB in use).
- 8 GB VRAM: the best quant that fits is Q4_K_M (5.3 GB file, about 7.2 GB in use).
- 12 GB VRAM: the best quant that fits is Q8_0 (9.3 GB file, about 11.2 GB in use).
Which granite 4.2 8b heretic quant should you choose?
Q4_K_M is the usual starting point for granite 4.2 8b heretic: it balances file size and quality well. Here it is a 5.3 GB file.
The Q8_0 file is 9.3 GB, about 1.7 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.
If memory is tight, the smallest file is the first one in the table at 0.0 GB, with the quality trade-offs that come with fewer bits.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about granite 4.2 8b heretic
How much VRAM does granite 4.2 8b heretic need?
About 7.2 GB at Q4_K_M with an 8K context window. That is the 5.3 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.
Can I run granite 4.2 8b heretic on an 8 GB GPU?
Yes, with Q4_K_M: the 5.3 GB file needs about 7.2 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of granite 4.2 8b heretic GGUF?
It depends on the quant: file is 0.0 GB, IQ3_M is 4.1 GB, IQ4_XS is 4.8 GB, Q4_K_M is 5.3 GB, Q5_K_M is 6.3 GB, Q6_K is 7.2 GB and 1 more.
What context length does granite 4.2 8b heretic support?
The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 1.3 GB at 8K and 5.4 GB at 32K.
Where can I download granite 4.2 8b heretic GGUF?
The files are on Hugging Face in the richardyoung/granite-4.2-8b-heretic-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does granite 4.2 8b heretic use?
Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.
Can I run this model on 8 GB VRAM?
Yes, the IQ4_XS quant uses approximately 6.7 GB of VRAM at 8 k context.
Does this model support vision?
No, the model has no vision capabilities.
What license does it use?
Apache‑2.0, inherited from the base Granite model.